Skip to content

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

10 Commits
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 

Repository files navigation

disentangle oversampling model

data and code file

data preparation: mnist, fashion-mnist, celebA;

"pre_train.py"

  • used to pre-train a generator and classifier, the classifier use confidence estimation training, and the generator use beta-tcvae as the based model;

the setting parameter is in "main.py" and "pre_train.py";

note:

  • you need to initial the dataset in the dataset folder first, use
    python dataset.py

runing procedure:

  • first run
    python pre_train.py
  • then run
    python main.py

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

Packages

Contributors

Languages